CtrlK
BlogDocsLog inGet started
Tessl Logo

seo

Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization". Do NOT use for accessibility (use web-accessibility), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/skills-catalog/skills/(quality)/seo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-formatted SEO reference with excellent copy-paste-ready code and a useful prioritized audit checklist. Its weaknesses are length and single-file monolithic structure — much of the guidance is SEO convention Claude already knows, and the structured-data examples belong in a one-level-deep reference file. A concrete audit workflow with validation steps is also missing.

Suggestions

Split the five full JSON-LD examples (Organization, Article, Product, FAQ, Breadcrumbs) into a references/structured-data.md file and keep only one representative snippet plus a pointer inline, moving the skill toward one-level-deep progressive disclosure.

Add an explicit step-by-step audit workflow (e.g., 1. Run Lighthouse SEO audit, 2. Check the critical checklist, 3. Fix issues, 4. Validate with Rich Results Test and Search Console) with validation checkpoints instead of relying on the priority checklist alone.

Trim or compress the guidance Claude already knows — title/meta character limits, hyphenated lowercase URLs, single h1, mobile font sizes — down to a short checklist, keeping the body's unique value in the complete code templates.

DimensionReasoningScore

Conciseness

Formatting is lean (tables, checklists, tight code blocks, no padded prose), but the ~530-line body restates substantial basics Claude already knows — title tags of 50-60 characters, hyphenated lowercase URLs, a single h1, 150-160 character meta descriptions, 16px mobile font sizes. This fits anchor 3 (mostly efficient, some unnecessary content that could be tightened) better than 4, where over-explanation would be only minor.

3 / 5

Actionability

Every topic ships copy-paste-ready material: a complete robots.txt, sitemap XML, canonical/meta-robots/JSON-LD snippets (Organization, Article, Product, FAQ, Breadcrumbs), viewport and tap-target CSS, hreflang tags, plus concrete validator URLs (Rich Results Test, Schema.org Validator) and a prioritized audit checklist. This matches anchor 5 — fully executable examples covering the common cases.

5 / 5

Workflow Clarity

The prioritized audit checklist (Critical → High → Medium → Ongoing) and Tools table provide an implicit sequence, but there is no explicit multi-step workflow (audit → fix → validate) with validation checkpoints, matching anchor 3 (steps/checklist present but checkpoints implicit). Not 4, because a newcomer has to assemble their own order of operations; not 2, because the priority tiers and per-section guidance do sequence the work.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the body is a single ~530-line monolith; the five full JSON-LD examples and sitemap block are prime candidates for a separate reference file. Section headers and the bottom References list (external Google/Schema.org docs and sibling skills) give real structure, so this is anchor 3 (some structure, content that should be separate is inline) rather than 2 (no structure at all).

3 / 5

Total

14

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly answers both what and when, enumerates natural trigger phrases, and — unusually well — carves out negative boundaries with explicit redirects to sibling skills. The only mild weakness is that the core capability statement is a single general verb phrase rather than a list of concrete actions.

DimensionReasoningScore

Specificity

"Optimize for search engine visibility and ranking" names the domain and a primary action, and the trigger enumeration surfaces concrete tasks ("fix meta tags", "add structured data", "sitemap optimization"). This matches anchor 4 (several specific actions, minor gaps) rather than 3, because the quoted phrases double as an explicit task inventory, but not 5 since the what-clause itself is a single general verb phrase.

4 / 5

Completeness

Both parts are explicit: the what is stated up front ("Optimize for search engine visibility and ranking") and the when uses an explicit "Use when asked to" clause with concrete quoted trigger phrases. This clearly matches anchor 5; anchor 4's caveat ("when could be more explicit") does not apply because the triggers are fully enumerated.

5 / 5

Trigger Term Quality

Six natural quoted phrases ("improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", "search engine optimization") are exactly what a user would say. A few common variants are missing (e.g., "rank higher", "SEO audit", "meta descriptions"), which keeps it at anchor 4 rather than 5, and well above anchor 3 since synonyms and phrasings are covered.

4 / 5

Distinctiveness Conflict Risk

The description actively disambiguates with "Do NOT use for accessibility (use web-accessibility), performance (use core-web-vitals), or comprehensive site audits... (use web-quality-audit)", routing overlapping requests to named sibling skills. This is a clear niche with minimal conflict risk, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (533 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

14

/

16

Passed

Repository
tech-leads-club/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.